DROPGoogle launches Gemini 3.8 Flash TTS and Flash-Lite TTS///DROPGemini Omni brings 1080p generation to Google Vids///BREAKClaude Opus 5.5 is here: 1M context, $4 input / $20 output///BREAKOpenAI adds GPT-6 Sol and Luna to the GPT-6 family///PAPEROpus 5.5's system card documents gains—and evaluation limits///BREAKGrok 4.7 launches at $2 input / $6 output per million tokens///DROPGrok Voice Transcribe 2.0 targets difficult real-world audio///TRENDGoogle steers new Gemini API projects to 3.8 Flash or 3.5 Flash-Lite///DROPGoogle launches Gemini 3.8 Flash TTS and Flash-Lite TTS///DROPGemini Omni brings 1080p generation to Google Vids///BREAKClaude Opus 5.5 is here: 1M context, $4 input / $20 output///BREAKOpenAI adds GPT-6 Sol and Luna to the GPT-6 family///PAPEROpus 5.5's system card documents gains—and evaluation limits///BREAKGrok 4.7 launches at $2 input / $6 output per million tokens///DROPGrok Voice Transcribe 2.0 targets difficult real-world audio///TRENDGoogle steers new Gemini API projects to 3.8 Flash or 3.5 Flash-Lite///
DARC.DEV

[ LAB — LIVE · no model calls ]

Token Thermostat

Estimate a text-inference workload using the source-checked model rates. Adjust ordinary input, cache reads, cache writes, output and request count. See the total and the assumptions, including GPT-6 long-context multipliers, Gemini introductory pricing and DeepSeek peak/off-peak conditions.

All lab tools

Interactive workbench / no model calls

Enter disjoint tokens per request. Include billable reasoning in output. Requests are assumed to have the same usage profile.

Inputs are sent to this application's server for deterministic calculation and are not stored. Do not paste secrets or raw customer content.

How to use it

  1. 01

    Choose a text model with verified per-token rates. Voice and unverified prices are excluded.

  2. 02

    Enter disjoint token buckets per request: an input token is ordinary, a cache read or a cache write—not all three.

  3. 03

    Apply the number of requests and inspect the returned rate conditions. Download the assumptions and estimate as JSON.

Sources and methodology